Multi-Agent Conversation
Configured with Agent, Chat Trigger, LM Chat Open Router, Memory Buffer Window, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Trigger
- AI & models
- Routing
- Code
- Data store
- Transform
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| When chat message received | Trigger | Chat Trigger | See node parameters |
| AI Agent | AI & models | Agent | See node parameters |
| Loop Over Items | Routing | Loop Over Items | See node parameters |
| Extract mentions | Code | Code | See node parameters |
| Simple Memory | Data store | Memory Buffer Window | See node parameters |
| Set last Assistant message as input | Transform | Edit Fields | See node parameters |
| Set user message as input | Transform | Edit Fields | See node parameters |
| First loop? | Routing | If | See node parameters |
| Set lastAssistantMessage | Transform | Edit Fields | See node parameters |
| Combine and format responses | Code | Code | See node parameters |
| Define Global Settings | Code | Code | See node parameters |
| Define Agent Settings | Code | Code | See node parameters |
| OpenRouter Chat Model | AI & models | LM Chat Open Router | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
openRouterApi
Workflow notes
Step 1: Configure Settings Nodes
Step 1: Configure Settings Nodes
Edit the JSON in these nodes to:
- Configure details about you (the user)
- Define content that will appear in all system messages
- Define Agents.
For Agents, you can configure:
- How many you create
- Their names
- The LLM model they use (choose any that are available via OpenRouter)
- Agent-specific system prompt content
Step 2: Connect Agent to OpenRouter
Step 2: Connect Agent to OpenRouter
Set your OpenRouter credentials, and all other parameters including system messages and model selection are dynamically populated.
About this workflow
About this workflow
What does this workflow do? Enables you to initiate a conversation with multiple AI agents at once. Each agent can be configured with a unique name, system instructions, a different model.
How do I use it?
- Configure the settings nodes to create the Agents you need.
- Call one or more individual agents using @Name mentions in your messages. If your message does not have @mentions, all agents will be called, in random order.
Sticky Note4
How does it work? Settings are configured in the first two nodes after the chat trigger. Then @mentions in your message are extracted and fed into a loop. With each loop, the agent's system message and model are dynamically populated, avoiding the need to create multiple agent nodes and complex routing logic.
When all agents have had their say, their responses are combined and formatted. The use of a shared memory node enables multi-round conversations.
What are the limitations? Agents cannot call each other or respond in parallel. Agents' responses are not visible to the user until all agents have responded.
Multi-Agent Conversation
Multi-Agent Conversation
Purpose and structure
This folder contains the Multi-Agent Conversation workflow. Its executable nodes use agent, chatTrigger, code, if, lmChatOpenRouter, memoryBufferWindow, set, splitInBatches. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
When chat message received
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Stickynote/1926_Stickynote_Splitinbatches_Automation_Triggered.json MIT; preserve source notices.
Canvas section labels
These name areas of the original canvas; they do not include explanatory instructions.
- Scalable Multi-Agent Conversations